Run_model: Run a saved MaxEnt model in predictive mode on a tile of...

In MartinezLaura/CanHeMonR.MaxEnt: Application of MaxEnt for canopy health monitoring through airbone image analysis.

Description

Run a saved MaxEnt model on a the image data selected.

Usage

Run_model(predictor_dir, text_train_dir, MaxEntmodel_dir, fname_MaxEntmodel_r,
  output_dir, rastername, model_type, EOS)

Arguments

predictor_dir	Path where predictor layers are held, rasters. If EOS = FALSE predictor_dir is a path if EOS = True predictor_dir is the path plus the image to predict
text_train_dir	Path where .tifs of the textures associated with r_train_dir. It is really important to avoid errors on the execution to pass the same numer of textures per tile as in the MaxEnt model used
MaxEntmodel_dir	Path where the MaxEnt model file is held
fname_MaxEntmodel_r	Filename of the MaxEnt model saved in rdsdata format
output_dir	Path to write the output to
rastername	Character. Prefix to give the outputed raster image, for control versions
model_type	Character. Type of model of maxent you want to use: raw, logistic or cloglog
EOS	If EOS true the for loop will be avoided if False will work with a for loop. Default FALSE

Value

A raster image for each tile with the probabilities or cummulative probabilities of presence for each class

See Also

Depends on: calibrate_model.r

Examples

## Not run: 
Run_model(predictor_dir = "/H03_CANHEMON/Imagery/Portugal/ADS100/ortophotos_06032017/geotif/pt616000-4404000.tif",
                            text_train_dir <-'/home/martlur/Documents/TexturesAds/',
                            MaxEntmodel_dir = "/home/martlur/Documents/Dockers/docker6EOS/",
                            fname_MaxEntmodel_r = "samp10000_Pb.rdsdata",
                            output_dir = "/DATA/Results/Rcode/OutputRunSickTree",
                            rastername = "samp1000_",
                            model_type = 'cloglog',
                            loop = FALSE)

## End(Not run)

MartinezLaura/CanHeMonR.MaxEnt documentation built on May 17, 2019, 6:21 p.m.